b9641
Mirrored from llama.cpp releases for archival readability. Support the source by reading on the original site.
ggml-webgpu: improve i-quants mul_mat performance and speed up prefil…
Mirrored from llama.cpp releases for archival readability. Support the source by reading on the original site.
ggml-webgpu: improve i-quants mul_mat performance and speed up prefil…
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.